The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the neon CLI for administrative tasks, including project management, environment variable synchronization (neon env pull), and database diagnostics (neon inspect db). These operations are consistent with the skill's purpose as a database management tool provided by the vendor.
[INDIRECT_PROMPT_INJECTION]: The skill has an inherent indirect prompt injection surface typical for agents processing external data like database schemas, connection strings, and SQL query results.
Ingestion points: The skill ingests DATABASE_URL values, repository-based project configurations, and SQL schemas provided by the user.
Boundary markers: No specific boundary markers or delimiters are defined to isolate untrusted external content from the skill's core instructions.
Capability inventory: The skill possesses the ability to execute shell commands via the neon CLI and perform file system operations (reading and writing .env files).
Sanitization: No explicit sanitization or validation logic for user-provided schemas or SQL inputs is described within the skill body, relying on the underlying platform's standard protections.

neon-postgres